如何将前导零添加到pyspark dataframe列

pyspark.sql.functions.lpad(col, len, pad)

from pyspark.sql import SparkSession
from pyspark.sql.functions import lpad

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 创建示例DataFrame
data = [("1",), ("12",), ("123",)]
df = spark.createDataFrame(data, ["number"])

# 添加前导零到列中
df_with_zeros = df.withColumn("number_with_zeros", lpad(df["number"], 5, "0"))

# 显示结果
df_with_zeros.show()

+------+----------------+
|number|number_with_zeros|
+------+----------------+
|     1|           00001|
|    12|           00012|
|   123|           00123|
+------+----------------+